paravirt: refactor struct paravirt_ops into smaller pv_*_ops

This patch refactors the paravirt_ops structure into groups of
functionally related ops:

pv_info - random info, rather than function entrypoints
pv_init_ops - functions used at boot time (some for module_init too)
pv_misc_ops - lazy mode, which didn't fit well anywhere else
pv_time_ops - time-related functions
pv_cpu_ops - various privileged instruction ops
pv_irq_ops - operations for managing interrupt state
pv_apic_ops - APIC operations
pv_mmu_ops - operations for managing pagetables

There are several motivations for this:

1. Some of these ops will be general to all x86, and some will be
   i386/x86-64 specific.  This makes it easier to share common stuff
   while allowing separate implementations where needed.

2. At the moment we must export all of paravirt_ops, but modules only
   need selected parts of it.  This allows us to export on a case by case
   basis (and also choose which export license we want to apply).

3. Functional groupings make things a bit more readable.

Struct paravirt_ops is now only used as a template to generate
patch-site identifiers, and to extract function pointers for inserting
into jmp/calls when patching.  It is only instantiated when needed.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andi Kleen <ak@suse.de>
Cc: Zach Amsden <zach@vmware.com>
Cc: Avi Kivity <avi@qumranet.com>
Cc: Anthony Liguory <aliguori@us.ibm.com>
Cc: "Glauber de Oliveira Costa" <glommer@gmail.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>

2 files changed, 256 insertions, 203 deletions

diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index 9fa3fa9..19726e1 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -33,19 +33,23 @@ enum paravirt_lazy_mode {
 	PARAVIRT_LAZY_FLUSH = 3,
 };
 
-struct paravirt_ops
-{
+
+/* general info */
+struct pv_info {
 	unsigned int kernel_rpl;
 	int shared_kernel_pmd;
- 	int paravirt_enabled;
+	int paravirt_enabled;
 	const char *name;
+};
 
+struct pv_init_ops {
 	/*
-	 * Patch may replace one of the defined code sequences with arbitrary
-	 * code, subject to the same register constraints.  This generally
-	 * means the code is not free to clobber any registers other than EAX.
-	 * The patch function should return the number of bytes of code
-	 * generated, as we nop pad the rest in generic code.
+	 * Patch may replace one of the defined code sequences with
+	 * arbitrary code, subject to the same register constraints.
+	 * This generally means the code is not free to clobber any
+	 * registers other than EAX.  The patch function should return
+	 * the number of bytes of code generated, as we nop pad the
+	 * rest in generic code.
 	 */
 	unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
 			  unsigned long addr, unsigned len);
@@ -55,29 +59,28 @@ struct paravirt_ops
 	char *(*memory_setup)(void);
 	void (*post_allocator_init)(void);
 
-	void (*init_IRQ)(void);
-	void (*time_init)(void);
-
-	/*
-	 * Called before/after init_mm pagetable setup. setup_start
-	 * may reset %cr3, and may pre-install parts of the pagetable;
-	 * pagetable setup is expected to preserve any existing
-	 * mapping.
-	 */
-	void (*pagetable_setup_start)(pgd_t *pgd_base);
-	void (*pagetable_setup_done)(pgd_t *pgd_base);
-
 	/* Print a banner to identify the environment */
 	void (*banner)(void);
+};
+
+
+struct pv_misc_ops {
+	/* Set deferred update mode, used for batching operations. */
+	void (*set_lazy_mode)(enum paravirt_lazy_mode mode);
+};
+
+struct pv_time_ops {
+	void (*time_init)(void);
 
 	/* Set and set time of day */
 	unsigned long (*get_wallclock)(void);
 	int (*set_wallclock)(unsigned long);
 
-	/* cpuid emulation, mostly so that caps bits can be disabled */
-	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
-		      unsigned int *ecx, unsigned int *edx);
+	unsigned long long (*sched_clock)(void);
+	unsigned long (*get_cpu_khz)(void);
+};
 
+struct pv_cpu_ops {
 	/* hooks for various privileged instructions */
 	unsigned long (*get_debugreg)(int regno);
 	void (*set_debugreg)(int regno, unsigned long value);
@@ -87,41 +90,10 @@ struct paravirt_ops
 	unsigned long (*read_cr0)(void);
 	void (*write_cr0)(unsigned long);
 
-	unsigned long (*read_cr2)(void);
-	void (*write_cr2)(unsigned long);
-
-	unsigned long (*read_cr3)(void);
-	void (*write_cr3)(unsigned long);
-
 	unsigned long (*read_cr4_safe)(void);
 	unsigned long (*read_cr4)(void);
 	void (*write_cr4)(unsigned long);
 
-	/*
-	 * Get/set interrupt state.  save_fl and restore_fl are only
-	 * expected to use X86_EFLAGS_IF; all other bits
-	 * returned from save_fl are undefined, and may be ignored by
-	 * restore_fl.
-	 */
-	unsigned long (*save_fl)(void);
-	void (*restore_fl)(unsigned long);
-	void (*irq_disable)(void);
-	void (*irq_enable)(void);
-	void (*safe_halt)(void);
-	void (*halt)(void);
-
-	void (*wbinvd)(void);
-
-	/* MSR, PMC and TSR operations.
-	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
-	u64 (*read_msr)(unsigned int msr, int *err);
-	int (*write_msr)(unsigned int msr, u64 val);
-
-	u64 (*read_tsc)(void);
-	u64 (*read_pmc)(void);
-	unsigned long long (*sched_clock)(void);
-	unsigned long (*get_cpu_khz)(void);
-
 	/* Segment descriptor handling */
 	void (*load_tr_desc)(void);
 	void (*load_gdt)(const struct Xgt_desc_struct *);
@@ -140,18 +112,45 @@ struct paravirt_ops
 	void (*load_esp0)(struct tss_struct *tss, struct thread_struct *t);
 
 	void (*set_iopl_mask)(unsigned mask);
+
+	void (*wbinvd)(void);
 	void (*io_delay)(void);
 
+	/* cpuid emulation, mostly so that caps bits can be disabled */
+	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
+		      unsigned int *ecx, unsigned int *edx);
+
+	/* MSR, PMC and TSR operations.
+	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
+	u64 (*read_msr)(unsigned int msr, int *err);
+	int (*write_msr)(unsigned int msr, u64 val);
+
+	u64 (*read_tsc)(void);
+	u64 (*read_pmc)(void);
+
+	/* These two are jmp to, not actually called. */
+	void (*irq_enable_sysexit)(void);
+	void (*iret)(void);
+};
+
+struct pv_irq_ops {
+	void (*init_IRQ)(void);
+
 	/*
-	 * Hooks for intercepting the creation/use/destruction of an
-	 * mm_struct.
+	 * Get/set interrupt state.  save_fl and restore_fl are only
+	 * expected to use X86_EFLAGS_IF; all other bits
+	 * returned from save_fl are undefined, and may be ignored by
+	 * restore_fl.
 	 */
-	void (*activate_mm)(struct mm_struct *prev,
-			    struct mm_struct *next);
-	void (*dup_mmap)(struct mm_struct *oldmm,
-			 struct mm_struct *mm);
-	void (*exit_mmap)(struct mm_struct *mm);
+	unsigned long (*save_fl)(void);
+	void (*restore_fl)(unsigned long);
+	void (*irq_disable)(void);
+	void (*irq_enable)(void);
+	void (*safe_halt)(void);
+	void (*halt)(void);
+};
 
+struct pv_apic_ops {
 #ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * Direct APIC operations, principally for VMI.  Ideally
@@ -167,6 +166,34 @@ struct paravirt_ops
 				 unsigned long start_eip,
 				 unsigned long start_esp);
 #endif
+};
+
+struct pv_mmu_ops {
+	/*
+	 * Called before/after init_mm pagetable setup. setup_start
+	 * may reset %cr3, and may pre-install parts of the pagetable;
+	 * pagetable setup is expected to preserve any existing
+	 * mapping.
+	 */
+	void (*pagetable_setup_start)(pgd_t *pgd_base);
+	void (*pagetable_setup_done)(pgd_t *pgd_base);
+
+	unsigned long (*read_cr2)(void);
+	void (*write_cr2)(unsigned long);
+
+	unsigned long (*read_cr3)(void);
+	void (*write_cr3)(unsigned long);
+
+	/*
+	 * Hooks for intercepting the creation/use/destruction of an
+	 * mm_struct.
+	 */
+	void (*activate_mm)(struct mm_struct *prev,
+			    struct mm_struct *next);
+	void (*dup_mmap)(struct mm_struct *oldmm,
+			 struct mm_struct *mm);
+	void (*exit_mmap)(struct mm_struct *mm);
+
 
 	/* TLB operations */
 	void (*flush_tlb_user)(void);
@@ -191,15 +218,12 @@ struct paravirt_ops
 	void (*pte_update_defer)(struct mm_struct *mm,
 				 unsigned long addr, pte_t *ptep);
 
-#ifdef CONFIG_HIGHPTE
-	void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
-#endif
-
 #ifdef CONFIG_X86_PAE
 	void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
- 	void (*set_pte_present)(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+	void (*set_pte_present)(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte);
 	void (*set_pud)(pud_t *pudp, pud_t pudval);
- 	void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+	void (*pte_clear)(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 	void (*pmd_clear)(pmd_t *pmdp);
 
 	unsigned long long (*pte_val)(pte_t);
@@ -217,21 +241,40 @@ struct paravirt_ops
 	pgd_t (*make_pgd)(unsigned long pgd);
 #endif
 
-	/* Set deferred update mode, used for batching operations. */
-	void (*set_lazy_mode)(enum paravirt_lazy_mode mode);
+#ifdef CONFIG_HIGHPTE
+	void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
+#endif
+};
 
-	/* These two are jmp to, not actually called. */
-	void (*irq_enable_sysexit)(void);
-	void (*iret)(void);
+/* This contains all the paravirt structures: we get a convenient
+ * number for each function using the offset which we use to indicate
+ * what to patch. */
+struct paravirt_patch_template
+{
+	struct pv_init_ops pv_init_ops;
+	struct pv_misc_ops pv_misc_ops;
+	struct pv_time_ops pv_time_ops;
+	struct pv_cpu_ops pv_cpu_ops;
+	struct pv_irq_ops pv_irq_ops;
+	struct pv_apic_ops pv_apic_ops;
+	struct pv_mmu_ops pv_mmu_ops;
 };
 
-extern struct paravirt_ops paravirt_ops;
+extern struct pv_info pv_info;
+extern struct pv_init_ops pv_init_ops;
+extern struct pv_misc_ops pv_misc_ops;
+extern struct pv_time_ops pv_time_ops;
+extern struct pv_cpu_ops pv_cpu_ops;
+extern struct pv_irq_ops pv_irq_ops;
+extern struct pv_apic_ops pv_apic_ops;
+extern struct pv_mmu_ops pv_mmu_ops;
 
 #define PARAVIRT_PATCH(x)					\
-	(offsetof(struct paravirt_ops, x) / sizeof(void *))
+	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
 
-#define paravirt_type(type)					\
-	[paravirt_typenum] "i" (PARAVIRT_PATCH(type))
+#define paravirt_type(op)				\
+	[paravirt_typenum] "i" (PARAVIRT_PATCH(op)),	\
+	[paravirt_opptr] "m" (op)
 #define paravirt_clobber(clobber)		\
 	[paravirt_clobber] "i" (clobber)
 
@@ -258,7 +301,7 @@ unsigned paravirt_patch_call(void *insnbuf,
 			     const void *target, u16 tgt_clobbers,
 			     unsigned long addr, u16 site_clobbers,
 			     unsigned len);
-unsigned paravirt_patch_jmp(const void *target, void *insnbuf,
+unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
 			    unsigned long addr, unsigned len);
 unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
 				unsigned long addr, unsigned len);
@@ -271,14 +314,14 @@ int paravirt_disable_iospace(void);
 /*
  * This generates an indirect call based on the operation type number.
  * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_ops structure, and can therefore be freely
- * converted back into a structure offset.
+ * offset into the paravirt_patch_template structure, and can therefore be
+ * freely converted back into a structure offset.
  */
-#define PARAVIRT_CALL	"call *(paravirt_ops+%c[paravirt_typenum]*4);"
+#define PARAVIRT_CALL	"call *%[paravirt_opptr];"
 
 /*
- * These macros are intended to wrap calls into a paravirt_ops
- * operation, so that they can be later identified and patched at
+ * These macros are intended to wrap calls through one of the paravirt
+ * ops structs, so that they can be later identified and patched at
  * runtime.
  *
  * Normally, a call to a pv_op function is a simple indirect call:
@@ -301,7 +344,7 @@ int paravirt_disable_iospace(void);
  * The call instruction itself is marked by placing its start address
  * and size into the .parainstructions section, so that
  * apply_paravirt() in arch/i386/kernel/alternative.c can do the
- * appropriate patching under the control of the backend paravirt_ops
+ * appropriate patching under the control of the backend pv_init_ops
  * implementation.
  *
  * Unfortunately there's no way to get gcc to generate the args setup
@@ -409,36 +452,36 @@ int paravirt_disable_iospace(void);
 
 static inline int paravirt_enabled(void)
 {
-	return paravirt_ops.paravirt_enabled;
+	return pv_info.paravirt_enabled;
 }
 
 static inline void load_esp0(struct tss_struct *tss,
 			     struct thread_struct *thread)
 {
-	PVOP_VCALL2(load_esp0, tss, thread);
+	PVOP_VCALL2(pv_cpu_ops.load_esp0, tss, thread);
 }
 
-#define ARCH_SETUP			paravirt_ops.arch_setup();
+#define ARCH_SETUP			pv_init_ops.arch_setup();
 static inline unsigned long get_wallclock(void)
 {
-	return PVOP_CALL0(unsigned long, get_wallclock);
+	return PVOP_CALL0(unsigned long, pv_time_ops.get_wallclock);
 }
 
 static inline int set_wallclock(unsigned long nowtime)
 {
-	return PVOP_CALL1(int, set_wallclock, nowtime);
+	return PVOP_CALL1(int, pv_time_ops.set_wallclock, nowtime);
 }
 
 static inline void (*choose_time_init(void))(void)
 {
-	return paravirt_ops.time_init;
+	return pv_time_ops.time_init;
 }
 
 /* The paravirtualized CPUID instruction. */
 static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
 			   unsigned int *ecx, unsigned int *edx)
 {
-	PVOP_VCALL4(cpuid, eax, ebx, ecx, edx);
+	PVOP_VCALL4(pv_cpu_ops.cpuid, eax, ebx, ecx, edx);
 }
 
 /*
@@ -446,87 +489,87 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
  */
 static inline unsigned long paravirt_get_debugreg(int reg)
 {
-	return PVOP_CALL1(unsigned long, get_debugreg, reg);
+	return PVOP_CALL1(unsigned long, pv_cpu_ops.get_debugreg, reg);
 }
 #define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
 static inline void set_debugreg(unsigned long val, int reg)
 {
-	PVOP_VCALL2(set_debugreg, reg, val);
+	PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val);
 }
 
 static inline void clts(void)
 {
-	PVOP_VCALL0(clts);
+	PVOP_VCALL0(pv_cpu_ops.clts);
 }
 
 static inline unsigned long read_cr0(void)
 {
-	return PVOP_CALL0(unsigned long, read_cr0);
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0);
 }
 
 static inline void write_cr0(unsigned long x)
 {
-	PVOP_VCALL1(write_cr0, x);
+	PVOP_VCALL1(pv_cpu_ops.write_cr0, x);
 }
 
 static inline unsigned long read_cr2(void)
 {
-	return PVOP_CALL0(unsigned long, read_cr2);
+	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr2);
 }
 
 static inline void write_cr2(unsigned long x)
 {
-	PVOP_VCALL1(write_cr2, x);
+	PVOP_VCALL1(pv_mmu_ops.write_cr2, x);
 }
 
 static inline unsigned long read_cr3(void)
 {
-	return PVOP_CALL0(unsigned long, read_cr3);
+	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3);
 }
 
 static inline void write_cr3(unsigned long x)
 {
-	PVOP_VCALL1(write_cr3, x);
+	PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
 }
 
 static inline unsigned long read_cr4(void)
 {
-	return PVOP_CALL0(unsigned long, read_cr4);
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
 }
 static inline unsigned long read_cr4_safe(void)
 {
-	return PVOP_CALL0(unsigned long, read_cr4_safe);
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
 }
 
 static inline void write_cr4(unsigned long x)
 {
-	PVOP_VCALL1(write_cr4, x);
+	PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
 }
 
 static inline void raw_safe_halt(void)
 {
-	PVOP_VCALL0(safe_halt);
+	PVOP_VCALL0(pv_irq_ops.safe_halt);
 }
 
 static inline void halt(void)
 {
-	PVOP_VCALL0(safe_halt);
+	PVOP_VCALL0(pv_irq_ops.safe_halt);
 }
 
 static inline void wbinvd(void)
 {
-	PVOP_VCALL0(wbinvd);
+	PVOP_VCALL0(pv_cpu_ops.wbinvd);
 }
 
-#define get_kernel_rpl()  (paravirt_ops.kernel_rpl)
+#define get_kernel_rpl()  (pv_info.kernel_rpl)
 
 static inline u64 paravirt_read_msr(unsigned msr, int *err)
 {
-	return PVOP_CALL2(u64, read_msr, msr, err);
+	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
 }
 static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
 {
-	return PVOP_CALL3(int, write_msr, msr, low, high);
+	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
 }
 
 /* These should all do BUG_ON(_err), but our headers are too tangled. */
@@ -560,7 +603,7 @@ static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
 
 static inline u64 paravirt_read_tsc(void)
 {
-	return PVOP_CALL0(u64, read_tsc);
+	return PVOP_CALL0(u64, pv_cpu_ops.read_tsc);
 }
 
 #define rdtscl(low) do {			\
@@ -572,15 +615,15 @@ static inline u64 paravirt_read_tsc(void)
 
 static inline unsigned long long paravirt_sched_clock(void)
 {
-	return PVOP_CALL0(unsigned long long, sched_clock);
+	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
-#define calculate_cpu_khz() (paravirt_ops.get_cpu_khz())
+#define calculate_cpu_khz() (pv_time_ops.get_cpu_khz())
 
 #define write_tsc(val1,val2) wrmsr(0x10, val1, val2)
 
 static inline unsigned long long paravirt_read_pmc(int counter)
 {
-	return PVOP_CALL1(u64, read_pmc, counter);
+	return PVOP_CALL1(u64, pv_cpu_ops.read_pmc, counter);
 }
 
 #define rdpmc(counter,low,high) do {		\
@@ -591,61 +634,61 @@ static inline unsigned long long paravirt_read_pmc(int counter)
 
 static inline void load_TR_desc(void)
 {
-	PVOP_VCALL0(load_tr_desc);
+	PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
 }
 static inline void load_gdt(const struct Xgt_desc_struct *dtr)
 {
-	PVOP_VCALL1(load_gdt, dtr);
+	PVOP_VCALL1(pv_cpu_ops.load_gdt, dtr);
 }
 static inline void load_idt(const struct Xgt_desc_struct *dtr)
 {
-	PVOP_VCALL1(load_idt, dtr);
+	PVOP_VCALL1(pv_cpu_ops.load_idt, dtr);
 }
 static inline void set_ldt(const void *addr, unsigned entries)
 {
-	PVOP_VCALL2(set_ldt, addr, entries);
+	PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
 }
 static inline void store_gdt(struct Xgt_desc_struct *dtr)
 {
-	PVOP_VCALL1(store_gdt, dtr);
+	PVOP_VCALL1(pv_cpu_ops.store_gdt, dtr);
 }
 static inline void store_idt(struct Xgt_desc_struct *dtr)
 {
-	PVOP_VCALL1(store_idt, dtr);
+	PVOP_VCALL1(pv_cpu_ops.store_idt, dtr);
 }
 static inline unsigned long paravirt_store_tr(void)
 {
-	return PVOP_CALL0(unsigned long, store_tr);
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.store_tr);
 }
 #define store_tr(tr)	((tr) = paravirt_store_tr())
 static inline void load_TLS(struct thread_struct *t, unsigned cpu)
 {
-	PVOP_VCALL2(load_tls, t, cpu);
+	PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
 }
 static inline void write_ldt_entry(void *dt, int entry, u32 low, u32 high)
 {
-	PVOP_VCALL4(write_ldt_entry, dt, entry, low, high);
+	PVOP_VCALL4(pv_cpu_ops.write_ldt_entry, dt, entry, low, high);
 }
 static inline void write_gdt_entry(void *dt, int entry, u32 low, u32 high)
 {
-	PVOP_VCALL4(write_gdt_entry, dt, entry, low, high);
+	PVOP_VCALL4(pv_cpu_ops.write_gdt_entry, dt, entry, low, high);
 }
 static inline void write_idt_entry(void *dt, int entry, u32 low, u32 high)
 {
-	PVOP_VCALL4(write_idt_entry, dt, entry, low, high);
+	PVOP_VCALL4(pv_cpu_ops.write_idt_entry, dt, entry, low, high);
 }
 static inline void set_iopl_mask(unsigned mask)
 {
-	PVOP_VCALL1(set_iopl_mask, mask);
+	PVOP_VCALL1(pv_cpu_ops.set_iopl_mask, mask);
 }
 
 /* The paravirtualized I/O functions */
 static inline void slow_down_io(void) {
-	paravirt_ops.io_delay();
+	pv_cpu_ops.io_delay();
 #ifdef REALLY_SLOW_IO
-	paravirt_ops.io_delay();
-	paravirt_ops.io_delay();
-	paravirt_ops.io_delay();
+	pv_cpu_ops.io_delay();
+	pv_cpu_ops.io_delay();
+	pv_cpu_ops.io_delay();
 #endif
 }
 
@@ -655,121 +698,120 @@ static inline void slow_down_io(void) {
  */
 static inline void apic_write(unsigned long reg, unsigned long v)
 {
-	PVOP_VCALL2(apic_write, reg, v);
+	PVOP_VCALL2(pv_apic_ops.apic_write, reg, v);
 }
 
 static inline void apic_write_atomic(unsigned long reg, unsigned long v)
 {
-	PVOP_VCALL2(apic_write_atomic, reg, v);
+	PVOP_VCALL2(pv_apic_ops.apic_write_atomic, reg, v);
 }
 
 static inline unsigned long apic_read(unsigned long reg)
 {
-	return PVOP_CALL1(unsigned long, apic_read, reg);
+	return PVOP_CALL1(unsigned long, pv_apic_ops.apic_read, reg);
 }
 
 static inline void setup_boot_clock(void)
 {
-	PVOP_VCALL0(setup_boot_clock);
+	PVOP_VCALL0(pv_apic_ops.setup_boot_clock);
 }
 
 static inline void setup_secondary_clock(void)
 {
-	PVOP_VCALL0(setup_secondary_clock);
+	PVOP_VCALL0(pv_apic_ops.setup_secondary_clock);
 }
 #endif
 
 static inline void paravirt_post_allocator_init(void)
 {
-	if (paravirt_ops.post_allocator_init)
-		(*paravirt_ops.post_allocator_init)();
+	if (pv_init_ops.post_allocator_init)
+		(*pv_init_ops.post_allocator_init)();
 }
 
 static inline void paravirt_pagetable_setup_start(pgd_t *base)
 {
-	if (paravirt_ops.pagetable_setup_start)
-		(*paravirt_ops.pagetable_setup_start)(base);
+	(*pv_mmu_ops.pagetable_setup_start)(base);
 }
 
 static inline void paravirt_pagetable_setup_done(pgd_t *base)
 {
-	if (paravirt_ops.pagetable_setup_done)
-		(*paravirt_ops.pagetable_setup_done)(base);
+	(*pv_mmu_ops.pagetable_setup_done)(base);
 }
 
 #ifdef CONFIG_SMP
 static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 				    unsigned long start_esp)
 {
-	PVOP_VCALL3(startup_ipi_hook, phys_apicid, start_eip, start_esp);
+	PVOP_VCALL3(pv_apic_ops.startup_ipi_hook,
+		    phys_apicid, start_eip, start_esp);
 }
 #endif
 
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)
 {
-	PVOP_VCALL2(activate_mm, prev, next);
+	PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
 }
 
 static inline void arch_dup_mmap(struct mm_struct *oldmm,
 				 struct mm_struct *mm)
 {
-	PVOP_VCALL2(dup_mmap, oldmm, mm);
+	PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
 {
-	PVOP_VCALL1(exit_mmap, mm);
+	PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
 }
 
 static inline void __flush_tlb(void)
 {
-	PVOP_VCALL0(flush_tlb_user);
+	PVOP_VCALL0(pv_mmu_ops.flush_tlb_user);
 }
 static inline void __flush_tlb_global(void)
 {
-	PVOP_VCALL0(flush_tlb_kernel);
+	PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
 }
 static inline void __flush_tlb_single(unsigned long addr)
 {
-	PVOP_VCALL1(flush_tlb_single, addr);
+	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
 }
 
 static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 				    unsigned long va)
 {
-	PVOP_VCALL3(flush_tlb_others, &cpumask, mm, va);
+	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
 }
 
 static inline void paravirt_alloc_pt(struct mm_struct *mm, unsigned pfn)
 {
-	PVOP_VCALL2(alloc_pt, mm, pfn);
+	PVOP_VCALL2(pv_mmu_ops.alloc_pt, mm, pfn);
 }
 static inline void paravirt_release_pt(unsigned pfn)
 {
-	PVOP_VCALL1(release_pt, pfn);
+	PVOP_VCALL1(pv_mmu_ops.release_pt, pfn);
 }
 
 static inline void paravirt_alloc_pd(unsigned pfn)
 {
-	PVOP_VCALL1(alloc_pd, pfn);
+	PVOP_VCALL1(pv_mmu_ops.alloc_pd, pfn);
 }
 
 static inline void paravirt_alloc_pd_clone(unsigned pfn, unsigned clonepfn,
 					   unsigned start, unsigned count)
 {
-	PVOP_VCALL4(alloc_pd_clone, pfn, clonepfn, start, count);
+	PVOP_VCALL4(pv_mmu_ops.alloc_pd_clone, pfn, clonepfn, start, count);
 }
 static inline void paravirt_release_pd(unsigned pfn)
 {
-	PVOP_VCALL1(release_pd, pfn);
+	PVOP_VCALL1(pv_mmu_ops.release_pd, pfn);
 }
 
 #ifdef CONFIG_HIGHPTE
 static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
 {
 	unsigned long ret;
-	ret = PVOP_CALL2(unsigned long, kmap_atomic_pte, page, type);
+	ret = PVOP_CALL2(unsigned long, pv_mmu_ops.kmap_atomic_pte, page, type);
 	return (void *)ret;
 }
 #endif
@@ -777,162 +819,171 @@ static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
 static inline void pte_update(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep)
 {
-	PVOP_VCALL3(pte_update, mm, addr, ptep);
+	PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
 }
 
 static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
 				    pte_t *ptep)
 {
-	PVOP_VCALL3(pte_update_defer, mm, addr, ptep);
+	PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
 }
 
 #ifdef CONFIG_X86_PAE
 static inline pte_t __pte(unsigned long long val)
 {
-	unsigned long long ret = PVOP_CALL2(unsigned long long, make_pte,
+	unsigned long long ret = PVOP_CALL2(unsigned long long,
+					    pv_mmu_ops.make_pte,
 					    val, val >> 32);
 	return (pte_t) { ret, ret >> 32 };
 }
 
 static inline pmd_t __pmd(unsigned long long val)
 {
-	return (pmd_t) { PVOP_CALL2(unsigned long long, make_pmd, val, val >> 32) };
+	return (pmd_t) { PVOP_CALL2(unsigned long long, pv_mmu_ops.make_pmd,
+				    val, val >> 32) };
 }
 
 static inline pgd_t __pgd(unsigned long long val)
 {
-	return (pgd_t) { PVOP_CALL2(unsigned long long, make_pgd, val, val >> 32) };
+	return (pgd_t) { PVOP_CALL2(unsigned long long, pv_mmu_ops.make_pgd,
+				    val, val >> 32) };
 }
 
 static inline unsigned long long pte_val(pte_t x)
 {
-	return PVOP_CALL2(unsigned long long, pte_val, x.pte_low, x.pte_high);
+	return PVOP_CALL2(unsigned long long, pv_mmu_ops.pte_val,
+			  x.pte_low, x.pte_high);
 }
 
 static inline unsigned long long pmd_val(pmd_t x)
 {
-	return PVOP_CALL2(unsigned long long, pmd_val, x.pmd, x.pmd >> 32);
+	return PVOP_CALL2(unsigned long long, pv_mmu_ops.pmd_val,
+			  x.pmd, x.pmd >> 32);
 }
 
 static inline unsigned long long pgd_val(pgd_t x)
 {
-	return PVOP_CALL2(unsigned long long, pgd_val, x.pgd, x.pgd >> 32);
+	return PVOP_CALL2(unsigned long long, pv_mmu_ops.pgd_val,
+			  x.pgd, x.pgd >> 32);
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
-	PVOP_VCALL3(set_pte, ptep, pteval.pte_low, pteval.pte_high);
+	PVOP_VCALL3(pv_mmu_ops.set_pte, ptep, pteval.pte_low, pteval.pte_high);
 }
 
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pteval)
 {
 	/* 5 arg words */
-	paravirt_ops.set_pte_at(mm, addr, ptep, pteval);
+	pv_mmu_ops.set_pte_at(mm, addr, ptep, pteval);
 }
 
 static inline void set_pte_atomic(pte_t *ptep, pte_t pteval)
 {
-	PVOP_VCALL3(set_pte_atomic, ptep, pteval.pte_low, pteval.pte_high);
+	PVOP_VCALL3(pv_mmu_ops.set_pte_atomic, ptep,
+		    pteval.pte_low, pteval.pte_high);
 }
 
 static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, pte_t pte)
 {
 	/* 5 arg words */
-	paravirt_ops.set_pte_present(mm, addr, ptep, pte);
+	pv_mmu_ops.set_pte_present(mm, addr, ptep, pte);
 }
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval)
 {
-	PVOP_VCALL3(set_pmd, pmdp, pmdval.pmd, pmdval.pmd >> 32);
+	PVOP_VCALL3(pv_mmu_ops.set_pmd, pmdp,
+		    pmdval.pmd, pmdval.pmd >> 32);
 }
 
 static inline void set_pud(pud_t *pudp, pud_t pudval)
 {
-	PVOP_VCALL3(set_pud, pudp, pudval.pgd.pgd, pudval.pgd.pgd >> 32);
+	PVOP_VCALL3(pv_mmu_ops.set_pud, pudp,
+		    pudval.pgd.pgd, pudval.pgd.pgd >> 32);
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	PVOP_VCALL3(pte_clear, mm, addr, ptep);
+	PVOP_VCALL3(pv_mmu_ops.pte_clear, mm, addr, ptep);
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
 {
-	PVOP_VCALL1(pmd_clear, pmdp);
+	PVOP_VCALL1(pv_mmu_ops.pmd_clear, pmdp);
 }
 
 #else  /* !CONFIG_X86_PAE */
 
 static inline pte_t __pte(unsigned long val)
 {
-	return (pte_t) { PVOP_CALL1(unsigned long, make_pte, val) };
+	return (pte_t) { PVOP_CALL1(unsigned long, pv_mmu_ops.make_pte, val) };
 }
 
 static inline pgd_t __pgd(unsigned long val)
 {
-	return (pgd_t) { PVOP_CALL1(unsigned long, make_pgd, val) };
+	return (pgd_t) { PVOP_CALL1(unsigned long, pv_mmu_ops.make_pgd, val) };
 }
 
 static inline unsigned long pte_val(pte_t x)
 {
-	return PVOP_CALL1(unsigned long, pte_val, x.pte_low);
+	return PVOP_CALL1(unsigned long, pv_mmu_ops.pte_val, x.pte_low);
 }
 
 static inline unsigned long pgd_val(pgd_t x)
 {
-	return PVOP_CALL1(unsigned long, pgd_val, x.pgd);
+	return PVOP_CALL1(unsigned long, pv_mmu_ops.pgd_val, x.pgd);
 }
 
 static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
-	PVOP_VCALL2(set_pte, ptep, pteval.pte_low);
+	PVOP_VCALL2(pv_mmu_ops.set_pte, ptep, pteval.pte_low);
 }
 
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pteval)
 {
-	PVOP_VCALL4(set_pte_at, mm, addr, ptep, pteval.pte_low);
+	PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pteval.pte_low);
 }
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmdval)
 {
-	PVOP_VCALL2(set_pmd, pmdp, pmdval.pud.pgd.pgd);
+	PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, pmdval.pud.pgd.pgd);
 }
 #endif	/* CONFIG_X86_PAE */
 
 #define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
 static inline void arch_enter_lazy_cpu_mode(void)
 {
-	PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_CPU);
+	PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_CPU);
 }
 
 static inline void arch_leave_lazy_cpu_mode(void)
 {
-	PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_NONE);
+	PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_NONE);
 }
 
 static inline void arch_flush_lazy_cpu_mode(void)
 {
-	PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_FLUSH);
+	PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_FLUSH);
 }
 
 
 #define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 static inline void arch_enter_lazy_mmu_mode(void)
 {
-	PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_MMU);
+	PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_MMU);
 }
 
 static inline void arch_leave_lazy_mmu_mode(void)
 {
-	PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_NONE);
+	PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_NONE);
 }
 
 static inline void arch_flush_lazy_mmu_mode(void)
 {
-	PVOP_VCALL1(set_lazy_mode, PARAVIRT_LAZY_FLUSH);
+	PVOP_VCALL1(pv_misc_ops.set_lazy_mode, PARAVIRT_LAZY_FLUSH);
 }
 
 void _paravirt_nop(void);
@@ -957,7 +1008,7 @@ static inline unsigned long __raw_local_save_flags(void)
 				  PARAVIRT_CALL
 				  "popl %%edx; popl %%ecx")
 		     : "=a"(f)
-		     : paravirt_type(save_fl),
+		     : paravirt_type(pv_irq_ops.save_fl),
 		       paravirt_clobber(CLBR_EAX)
 		     : "memory", "cc");
 	return f;
@@ -970,7 +1021,7 @@ static inline void raw_local_irq_restore(unsigned long f)
 				  "popl %%edx; popl %%ecx")
 		     : "=a"(f)
 		     : "0"(f),
-		       paravirt_type(restore_fl),
+		       paravirt_type(pv_irq_ops.restore_fl),
 		       paravirt_clobber(CLBR_EAX)
 		     : "memory", "cc");
 }
@@ -981,7 +1032,7 @@ static inline void raw_local_irq_disable(void)
 				  PARAVIRT_CALL
 				  "popl %%edx; popl %%ecx")
 		     :
-		     : paravirt_type(irq_disable),
+		     : paravirt_type(pv_irq_ops.irq_disable),
 		       paravirt_clobber(CLBR_EAX)
 		     : "memory", "eax", "cc");
 }
@@ -992,7 +1043,7 @@ static inline void raw_local_irq_enable(void)
 				  PARAVIRT_CALL
 				  "popl %%edx; popl %%ecx")
 		     :
-		     : paravirt_type(irq_enable),
+		     : paravirt_type(pv_irq_ops.irq_enable),
 		       paravirt_clobber(CLBR_EAX)
 		     : "memory", "eax", "cc");
 }
@@ -1008,21 +1059,23 @@ static inline unsigned long __raw_local_irq_save(void)
 
 #define CLI_STRING							\
 	_paravirt_alt("pushl %%ecx; pushl %%edx;"			\
-		      "call *paravirt_ops+%c[paravirt_cli_type]*4;"	\
+		      "call *%[paravirt_cli_opptr];"			\
 		      "popl %%edx; popl %%ecx",				\
 		      "%c[paravirt_cli_type]", "%c[paravirt_clobber]")
 
 #define STI_STRING							\
 	_paravirt_alt("pushl %%ecx; pushl %%edx;"			\
-		      "call *paravirt_ops+%c[paravirt_sti_type]*4;"	\
+		      "call *%[paravirt_sti_opptr];"			\
 		      "popl %%edx; popl %%ecx",				\
 		      "%c[paravirt_sti_type]", "%c[paravirt_clobber]")
 
 #define CLI_STI_CLOBBERS , "%eax"
 #define CLI_STI_INPUT_ARGS						\
 	,								\
-	[paravirt_cli_type] "i" (PARAVIRT_PATCH(irq_disable)),		\
-	[paravirt_sti_type] "i" (PARAVIRT_PATCH(irq_enable)),		\
+	[paravirt_cli_type] "i" (PARAVIRT_PATCH(pv_irq_ops.irq_disable)),		\
+	[paravirt_cli_opptr] "m" (pv_irq_ops.irq_disable),		\
+	[paravirt_sti_type] "i" (PARAVIRT_PATCH(pv_irq_ops.irq_enable)),		\
+	[paravirt_sti_opptr] "m" (pv_irq_ops.irq_enable),		\
 	paravirt_clobber(CLBR_EAX)
 
 /* Make sure as little as possible of this mess escapes. */
@@ -1042,7 +1095,7 @@ static inline unsigned long __raw_local_irq_save(void)
 
 #else  /* __ASSEMBLY__ */
 
-#define PARA_PATCH(off)	((off) / 4)
+#define PARA_PATCH(struct, off)	((PARAVIRT_PATCH_##struct + (off)) / 4)
 
 #define PARA_SITE(ptype, clobbers, ops)		\
 771:;						\
@@ -1055,29 +1108,29 @@ static inline unsigned long __raw_local_irq_save(void)
 	 .short clobbers;			\
 	.popsection
 
-#define INTERRUPT_RETURN					\
-	PARA_SITE(PARA_PATCH(PARAVIRT_iret), CLBR_NONE,		\
-		  jmp *%cs:paravirt_ops+PARAVIRT_iret)
+#define INTERRUPT_RETURN						\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,	\
+		  jmp *%cs:pv_cpu_ops+PV_CPU_iret)
 
 #define DISABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(PARAVIRT_irq_disable), clobbers,		\
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
 		  pushl %eax; pushl %ecx; pushl %edx;			\
-		  call *%cs:paravirt_ops+PARAVIRT_irq_disable;		\
+		  call *%cs:pv_irq_ops+PV_IRQ_irq_disable;		\
 		  popl %edx; popl %ecx; popl %eax)			\
 
 #define ENABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(PARAVIRT_irq_enable), clobbers,		\
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
 		  pushl %eax; pushl %ecx; pushl %edx;			\
-		  call *%cs:paravirt_ops+PARAVIRT_irq_enable;		\
+		  call *%cs:pv_irq_ops+PV_IRQ_irq_enable;		\
 		  popl %edx; popl %ecx; popl %eax)
 
-#define ENABLE_INTERRUPTS_SYSEXIT					\
-	PARA_SITE(PARA_PATCH(PARAVIRT_irq_enable_sysexit), CLBR_NONE,	\
-		  jmp *%cs:paravirt_ops+PARAVIRT_irq_enable_sysexit)
+#define ENABLE_INTERRUPTS_SYSEXIT					       \
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), CLBR_NONE,\
+		  jmp *%cs:pv_cpu_ops+PV_CPU_irq_enable_sysexit)
 
 #define GET_CR0_INTO_EAX			\
 	push %ecx; push %edx;			\
-	call *paravirt_ops+PARAVIRT_read_cr0;	\
+	call *pv_cpu_ops+PV_CPU_read_cr0;	\
 	pop %edx; pop %ecx
 
 #endif /* __ASSEMBLY__ */
diff --git a/include/asm-x86/pgtable-3level-defs.h b/include/asm-x86/pgtable-3level-defs.h
index c0df89f..448ac95 100644
--- a/include/asm-x86/pgtable-3level-defs.h
+++ b/include/asm-x86/pgtable-3level-defs.h
@@ -2,7 +2,7 @@
 #define _I386_PGTABLE_3LEVEL_DEFS_H
 
 #ifdef CONFIG_PARAVIRT
-#define SHARED_KERNEL_PMD	(paravirt_ops.shared_kernel_pmd)
+#define SHARED_KERNEL_PMD	(pv_info.shared_kernel_pmd)
 #else
 #define SHARED_KERNEL_PMD	1
 #endif